Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Spatially-Lucid AI Classification in Non-Euclidean Space: An Application for MxIF Oncology Data

Majid Farhadloo, Arun Sharma, Jayant Gupta, Alexey Leontovich, Svetomir N. Markovic, Shashi Shekhar

TL;DR

The paper tackles spatially-lucid classification of multi-category point sets in non-Euclidean space, addressing spatial variability across place-types and the need for interpretability in oncology contexts. It introduces a spatial ensemble framework where network parameters are map weights that vary by place-type, augmented with weighted-distance learning rates and spatial domain adaptation to handle limited data and domain shifts. Empirical evaluation on MxIF oncology data shows substantial performance gains over one-size-fits-all baselines, with SAMCNet-based implementations delivering the strongest improvements and permutation-based explanations highlighting meaningful spatial interactions. The work advances interpretable modeling of immune–tumor spatial patterns and offers practical pathways to support decision-making and immunotherapy design.

Abstract

Given multi-category point sets from different place-types, our goal is to develop a spatially-lucid classifier that can distinguish between two classes based on the arrangements of their points. This problem is important for many applications, such as oncology, for analyzing immune-tumor relationships and designing new immunotherapies. It is challenging due to spatial variability and interpretability needs. Previously proposed techniques require dense training data or have limited ability to handle significant spatial variability within a single place-type. Most importantly, these deep neural network (DNN) approaches are not designed to work in non-Euclidean space, particularly point sets. Existing non-Euclidean DNN methods are limited to one-size-fits-all approaches. We explore a spatial ensemble framework that explicitly uses different training strategies, including weighted-distance learning rate and spatial domain adaptation, on various place-types for spatially-lucid classification. Experimental results on real-world datasets (e.g., MxIF oncology data) show that the proposed framework provides higher prediction accuracy than baseline methods.

Towards Spatially-Lucid AI Classification in Non-Euclidean Space: An Application for MxIF Oncology Data

TL;DR

The paper tackles spatially-lucid classification of multi-category point sets in non-Euclidean space, addressing spatial variability across place-types and the need for interpretability in oncology contexts. It introduces a spatial ensemble framework where network parameters are map weights that vary by place-type, augmented with weighted-distance learning rates and spatial domain adaptation to handle limited data and domain shifts. Empirical evaluation on MxIF oncology data shows substantial performance gains over one-size-fits-all baselines, with SAMCNet-based implementations delivering the strongest improvements and permutation-based explanations highlighting meaningful spatial interactions. The work advances interpretable modeling of immune–tumor spatial patterns and offers practical pathways to support decision-making and immunotherapy design.

Abstract

Given multi-category point sets from different place-types, our goal is to develop a spatially-lucid classifier that can distinguish between two classes based on the arrangements of their points. This problem is important for many applications, such as oncology, for analyzing immune-tumor relationships and designing new immunotherapies. It is challenging due to spatial variability and interpretability needs. Previously proposed techniques require dense training data or have limited ability to handle significant spatial variability within a single place-type. Most importantly, these deep neural network (DNN) approaches are not designed to work in non-Euclidean space, particularly point sets. Existing non-Euclidean DNN methods are limited to one-size-fits-all approaches. We explore a spatial ensemble framework that explicitly uses different training strategies, including weighted-distance learning rate and spatial domain adaptation, on various place-types for spatially-lucid classification. Experimental results on real-world datasets (e.g., MxIF oncology data) show that the proposed framework provides higher prediction accuracy than baseline methods.
Paper Structure (15 sections, 3 equations, 8 figures, 4 tables)

This paper contains 15 sections, 3 equations, 8 figures, 4 tables.

Table of Contents

  1. Introduction
  2. An Illustrative Application Domain
  3. Related Work
  4. Problem Formulation
  5. Basic concepts
  6. Problem Statement
  7. Proposed Approach
  8. Place-type-based
  9. Weighted-distance learning rate:
  10. Spatial domain adaptation (SDA):
  11. Validation
  12. Experimental Design:
  13. Experiment Results
  14. Case Study
  15. Conclusion & Future Work

Figures (8)

  • Figure 1: An illustration of the spatial differences in arrangements between two class labels of multi-category point sets from different spatial domains.
  • Figure 2: Spatial variability in a tissue slide, emphasized by pathology-driven fields of view (FOVs, colored squares), reveals distinct patterns within each FOV.
  • Figure 3: Related works on multi-category point sets for spatially-lucid classification.
  • Figure 4: Three multi-category point sets (i.e., pathology-driven fields of view) are categorized based on tumor infiltration.
  • Figure 5: Spatially-lucid classifiers for distinguishing between two class labels belonging to distinct place-types (tumor and interface) based on two types of 3-way spatial arrangements.
  • ...and 3 more figures

Theorems & Definitions (7)

  • Definition 1
  • Definition 2
  • Definition 3
  • Definition 4
  • Definition 5
  • Definition 6
  • Definition 7